Software Snack Bites cover image

#12 - Phillip Carter (Principal PM @ Honeycomb) - All The Hard Stuff when Building Products with LLMs, Actual Results from Leveraging AI

Software Snack Bites

00:00

How to Use Query Assistants to Query the Database

Honeycomb runs on just Lambda and S3. It's trivially parallelizable. We can spin up to like 30k lambdas for a given query if we need to, which one of our customers has done to us before. The only time that something actually makes it into the database is when we have a valid query that comes out. And in practice, that tends to pretty much capture everything within our product that people care about. So yeah, because we're not actually in a position where touching customer data with this LLM in some way, it's pretty safe for us to deploy.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app